Professional Documents
Culture Documents
2
M.Dhivya 1Dr.M.Renuka Devi,
1
Director, Department of MCA,
Sri venkateswara College of Computer Application and Management, Coimbatore.
2
Assistant Professor, Department of Computer Science,
VLB Janakiammal College of Arts & Science
Cum Research Scholar, Bharathiar University, Coimbatore.
Abstract: In Textile Industry, Quality of the Fabric is the main important factor. At the initial stage, it is very essential to identify and avoid the
fabrics faults/defects and hence human perception consumes lot of time and cost to reveal the fabrics faults. Now-a-days Automated Inspection
Systems are very useful to decrease the fault prediction time and gives best visualizing clarity- based on computer vision and image processing
techniques. This paper made an extended review about the quality parameters in the fiber-to-fabric process, fabrics defects detection
terminologies applied on major three clusters of fabric defects knitting, woven and sewing fabric defects. And this paper also explains about the
statistical performance measures which are used to analyze the defect detection process. Also, comparison among the methods proposed in the
field of fabric defect detection.
Keywords: Fabrics Defects; Fabric faults; Fabric defects terminology; Thresholding; fabric defect identification system
__________________________________________________*****_________________________________________________.
I. INTRODUCTION review on the all the methods which is applicable in all the
The textile industry is vertically-integrated across stages of fabric production process.
the value chain and extends from fiber to fabric to garments.
At the same time, it is a highly-fragmented sector, and
comprises small-scale, non-integrated spinning, weaving,
processing and cloth manufacturing enterprises.
Some of the Faults that commonly identified in the
fabric types are skewed or Bias, Back Fabric Seam
Impression ,Birdseye, Bowing ,Color Out, Color Smear,
Crease Mark, Crease Streak, Drop Stitches, Dye Streak In
Printing, End Out ,Jerk-in, Knots ,Missing Yarn ,Mixed End
(yarn) Mottled, Needle Line, Open Reed ,Pin ,Press-Off
, Printing Machine Stop ,Print Out of Repair ,Puckered
Selvage and Runner Sanforized Pucker Scrimp. The
purposes of visual inspection and decision making schemes
that are able to discriminate the features are extracted from
normal and defective regions. On the basis of nature of
features from the fabric surfaces, the proposed approaches
have been characterized into three categories: knitting,
woven and sewing defects.
These defects are occurred in any one of the stage of fabric
production process. The entire process of fabric production
is described in Figure-1. Any fault occurs in between this
flow of process will leads to faulty production result. So
keep track the entire process is the best way to deliver the
perfect material. While analyzing the fault prediction
method available in the context one should gives the deep
965
971
972
The Figure-3 explains the analysis of few methods and its examined defects based on the review papers.
The equation listed in Table-1 is used to calculate the detailed explanation about the publication, methods applied
performance measure of the fabric detection system on it, which type of defects are experimented or identified
statistically. These statistical measures may be used to plot and derived grading efficiency are given.
the results graphically and to evaluate the system and
compression with other state-of-art systems. In Table-2 the
TP
1 Sensitivity
TP FN
TN
2 Specificity
FP TN
TP
3 Precision
TP FP
973
Grading
S.
Title & Year of Publication Methods Applied Defects Experimented Efficienc
No
y
Automated Fabric fault
detection using Morpho Bitplane decomposition &
1 Woven fabric defects 93.2%
logical operation on Bit Weighted morphology
plane,2015[73]
Novel image
Automated patterned fabric Envision defective objects in
2 Decomposition method 95%
fault detection ,2015 patterned fabric image
ANN classifier
machine faults, hole, Color
Fabric fault processing using
bleed, problems ,scratch poor
3 image processing Histrogram, Thresholding 86%
finishing ,dirt spot, excessive
Techniques,2015[74]
stretching ,crack point
Automated patterned fabric Histrogram,
4 Patterned Fabric Defects 95%
fault detection, 2015[75] Thresholding,Gray Scale
Evaluation of yarn quality in IP-Mathematical
5 Thickness of yarn 85%
fabric, 2014 (Stat)Model
Hole,stain,miss-pick,miss-
Defect detection in fabric
end,double-pick,double- D >=20-
6 images using SVD SVD Technique
end,weft-float,wrap- Defects
techniques,2014[76]
float,course-pick,course-end
Fabric Fault processing Hole,Sctrach,Fading,Broken
7 perfections & Histrogram, Thresholding ends,broken 85%
imperfection,2014[77] picks,float,gout,cut
Texture defect detection using DCT/H-image method, 96.01 to
8 Local Homo -geneity & Multivariate statistics
Common fabric defects
DCT,2014[78] method 97.8%
Yarn parameterization & Artificial intelligence Yarn faults-thin & thick
9 90%
fabric prediction 2013[79] Method places &neps
Measuring the roughness of
10 knitted fabrics by analysis of Kawabata Method Knitted fabric roughness 88%
surface signals 2013[80]
Fabric fault processing using Global thresholding &
Broken ends,broken
11 image processing technique Local or Adaptive 85%
picks,float,gout,hole,cut
2013[81] Thresholding
Fabric defect detection based
12 on GLCM & Gabour filter GLCM & Gabour filter Blob shaped,edge shaped 94%
2013[82]
13 Real Time fabric defect GLCM Texture defect 88%
974
VI. CONCLUSION [10] Heidari, N., Azmi, R., & Pishgoo, B. (2011). Fabric textile
In this paper, major defect detection techniques are surveyed defect detection, by selecting a suitable subset of wavelet
based on three fabric defects namely knitting, woven and coefficients, through genetic algorithm. International
Journal of Image Processing (IJIP), 5(1), 25.
sewing fabrics. According to this survey we found that the
[11] 11.. Chan, C. H., & Pang, G. K. (2000). Fabric defect
system is fully automatic as well as defect is detected in all
detection by Fourier analysis. Industry Applications, IEEE
sort of steps in fabric production process is needed. The Transactions on, 36(5), 1267-1276.
application methodology opted for each fabric type is [12] Tsai, D. M., & Huang, T. Y. (2003). Automated surface
dissimilar to one another. We hope that this paper would be inspection for statistical textures. Image and Vision
useful for every newcomer to the area of automated fabric computing, 21(4), 307-323.
defect inspection. The comprehensive survey presented in [13] Yang, X. Z., Pang, G. K., & Yung, N. H. (2002).
this paper will be useful to develop and analyze a novel Discriminative fabric defect detection using adaptive
approach. wavelets. Optical Engineering, 41(12), 3116-3126.
[14] Yang, X., Pang, G., & Yung, N. (2005, December). Robust
fabric defect detection and classification using multiple
REFERENCE
adaptive wavelets. In Vision, Image and Signal Processing,
[1] Kumar, A. (2008). Computer-vision-based fabric defect
IEE Proceedings- (Vol. 152, No. 6, pp. 715-723). IET.
detection: a survey. Industrial Electronics, IEEE
[15] Sheen, S. H., Chien, H. T., Lawrence, W. P., & Raptis, A. C.
Transactions on, 55(1), 348-363.
(1997). U.S. Patent No. 5,665,907. Washington, DC: U.S.
[2] Kuo, C. F. J., & Su, T. L. (2003). Gray relational analysis
Patent and Trademark Office.
for recognizing fabric defects. Textile Research
[16] Li, Z., Liu, J., Liu, J., & Gao, W. (2014). Fabric defect
Journal, 73(5), 461-465.
segmentation by bidimensional empirical mode
[3] Yldz, Kazm, Ali Buldu, and Mustafa Demetgul. "A
decomposition. Textile Research Journal,84(7), 704-713.
thermal-based defect classification method in textile fabrics
[17] 17.. Karayiannis, Y.A., Stojanovic, R., Mitropoulos, P.,
with K-nearest neighbor algorithm."Journal of Industrial
Koulamas, C., Stouraitis, T., Koubias, S., Papadopoulos, G.,
Textiles (2014): 1528083714555777.
Defect detection and classification on web textile fabric
[4] Wen, Z., Cao, J., Liu, X., & Ying, S. (2014). Fabric defects
using multiresolution decomposition and neural networks,
detection using adaptive wavelets. International Journal of
Proceedings of 6th IEEE International Conference on
Clothing Science and Technology,26(3), 202-211.
Electronics, Circuits and Systems, 5-8 Sep 1999, pp.765-768.
[5] Li, W., Xue, W., & Cheng, L. (2012). Intelligent detection of
[18] Zhang, Y. H., Yuen, C. W. M., Wong, W. K., & Kan, C. W.
defects of yarn-dyed fabrics by energy-based local binary
(2011). An intelligent model for detecting and classifying
patterns. Textile Research Journal, 82(19), 1960-1972.
color-textured fabric defects using genetic algorithms and the
[6] Latif-Amet, A., Ertzn, A., & Eril, A. (2000). An efficient
Elman neural network. Textile Research Journal, 81(17),
method for texture defect detection: sub-band domain co-
1772-1787.
occurrence matrices. Image and Vision computing, 18(6),
[19] Shi, M., Fu, R., Guo, Y., Bai, S., & Xu, B. (2011). Fabric
543-553.
defect detection using local contrast deviations. Multimedia
[7] Raheja, J. L., Ajay, B., & Chaudhary, A. (2013). Real time
Tools and Applications, 52(1), 147-157.
fabric defect detection system on an embedded DSP
[20] Amet, A. L., Ertuzun, A., & Ercil, A. (1998, April). Texture
platform. Optik-International Journal for Light and Electron
defect detection using subband domain co-occurrence
Optics, 124(21), 5280-5284.
matrices. In Image Analysis and Interpretation, 1998 IEEE
[8] Tsai, D. M., & Chiang, C. H. (2003). Automatic band
Southwest Symposium on (pp. 205-210). IEEE.
selection for wavelet reconstruction in the application of
[21] Saeidi, R. G., Latifi, M., Najar, S. S., & Saeidi, A. G. (2005).
defect detection. Image and Vision Computing, 21(5), 413-
Computer vision-aided fabric inspection system for on-
431.
circular knitting machine. Textile Research Journal, 75(6),
[9] Yang, X., Pang, G., & Yung, N. (2004). Discriminative
492-497.
training approaches to fabric defect classification based on
[22] Shady, E., Gowayed, Y., Abouiiana, M., Youssef, S., &
wavelet transform. Pattern Recognition,37(5), 889-899.
Pastore, C. (2006). Detection and classification of defects in
975
977